Glossary · Term

fast weight

← all terms

Definition

Plain language

A small running summary inside a sequence model that gets updated as new tokens arrive.

As stated in the literature

A fixed-size recurrent state (matrix or vector) in state-space and linear-attention models that compresses sequence history through gated overwrites; contrasts with the lossless but growing KV cache of attention layers.

Also called: fast weights

Why it matters: It lets sequence models keep memory cost bounded as context grows, which is the central tradeoff with attention's exact but expanding KV cache.

For example, in a linear-attention layer the model maintains a small matrix that gets updated with each new token and acts as a compact stand-in for everything seen so far.

Heard on the show

“They call these "fast weights.”
Episode 114 — Agents That Rewrite Their Own Weights Instead of Just Taking Notes

Mentioned in 2 episodes

  1. 114
    Agents That Rewrite Their Own Weights Instead of Just Taking Notes
  2. 085
    Why Long-Context Models Might Need Compute, Not Capacity, Before Eviction

Related terms